> ## Documentation Index
> Fetch the complete documentation index at: https://phaseo.app/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Citation

> How to acknowledge Phaseo data, benchmarks, and gateway tooling in your work.

Phaseo aggregates public information and benchmark results from model providers and evaluation projects.
If you rely on Phaseo to look up, compare, or monitor models, a simple acknowledgement helps others discover the platform.

***

## Quick version

If Phaseo was helpful, please just link to it somewhere appropriate (methods, footnote, or acknowledgements):

> This work uses model metadata and aggregated benchmark results from [Phaseo](https://phaseo.app).

***

## Suggested citation (optional)

If you prefer a more formal reference, you can use:

```text theme={null}
Phaseo. (2025). Phaseo: Aggregated benchmarks and gateway for AI models. https://phaseo.app
```

BibTeX (optional):

```bibtex theme={null}
@misc{phaseo-2025,
    title  = {Phaseo: Aggregated benchmarks and gateway for AI models},
    author = {{Phaseo Team}},
    year   = {2025},
    url    = {https://phaseo.app}
}
```

***

## Benchmark data

Phaseo **does not run benchmarks itself**. We surface and normalise scores reported by benchmark authors and model providers.

When you use benchmark results that you accessed via Phaseo:

1. Cite the original benchmark and paper as the primary source.
2. Optionally acknowledge Phaseo as the place you retrieved or compared the scores.
3. Include:

* Benchmark name and split (for example `MMLU test`).
* Model identifier and provider.
* URL to the relevant Phaseo page or API.
* Date accessed.

Example text:

> Benchmark scores were retrieved via Phaseo (MMLU test split), accessed 3 March 2025. Model: `openai-gpt-4o`, provider: OpenAI.

## Gateway and tooling

When describing integrations, you can mention Phaseo as the gateway layer rather than as a research benchmark source:

> "We used the Phaseo Gateway to unify access to OpenAI, Anthropic, and Google models through a single API."

Link directly to the [API reference](../api-reference/introduction.mdx) so readers can explore further.